Safety of artificial superintelligence

Abstract

The paper analyses an important problem of cyber security from human safety perspective which is usually described as data and/or computer safety itself without mentioning the human. There are numerous scientific predictions of creation of artificial superintelligence, which could arise in the near future. That is why the strong necessity for protection of such a system from causing any farm arises. This paper reviews approaches and methods already presented for solving this problem in a single article, analyses its results and provides future research directions.